© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49965
    Prev
    Next
    INDEX
    Explanations

    considerably rapidly dramatically significantly greatly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ator
    -0.09
    åij¼åĴĮ
    -0.09
    _bs
    -0.09
    æĶ¾è¿ĩ
    -0.08
    loh
    -0.08
    èĪħ
    -0.08
    éŁ³åĵį
    -0.08
    à¤Ľ
    -0.08
    ated
    -0.08
    undry
    -0.08
    POSITIVE LOGITS
    ç½ķ
    0.10
    ulg
    0.09
    å®ĺæĸ¹
    0.09
     unofficial
    0.08
     Mand
    0.08
    æĬĽ
    0.08
    鬼
    0.08
    /packages
    0.08
    éĶIJ
    0.08
    å°¸
    0.08
    Activations Density 0.044%

    No Known Activations